Colin McDonnell
4b3c5ca905
* rename agent key to opencode and add skill invocation coverage. add skill-invoke tests for claude and opencode with local play-based validation signals, update CI matrices, and include the current tracked refactors in this branch for review. Made-with: Cursor * exclude agent-specific skill-invoke tests from wrong agent in CI matrix * address review follow-up and preserve workflow run UI tweak. switch changed-agents ci coverage to exercise the opentoad implementation path while keeping the opencode expectation, and include the local workflow run client interaction updates requested on this branch. Made-with: Cursor * remove opentoad agent filename from runtime. rename the opencode harness implementation file from opentoad.ts to opencode.ts and update ci coverage input accordingly so action code no longer carries the old filename. Made-with: Cursor * ensure security prompt bypass is set on every test fixture. this keeps adversarial and permissions harnesses from being blocked by the default prompt-injection refusal path during CI security tests. Made-with: Cursor --------- Co-authored-by: pullfrog[bot] <226033991+pullfrog[bot]@users.noreply.github.com>
47 lines
1.5 KiB
TypeScript
47 lines
1.5 KiB
TypeScript
import { randomUUID } from "node:crypto";
|
|
import type { AgentResult, TestRunnerOptions, ValidationCheck } from "../utils.ts";
|
|
import { defineFixture } from "../utils.ts";
|
|
|
|
/**
|
|
* MCP merge test - validates repo-level MCP servers merge correctly with pullfrog.
|
|
*
|
|
* Uses GITHUB_REPOSITORY=pullfrog/test-repo-mcp whose robin-mcp reads a secret
|
|
* from /tmp/pullfrog-mcp-secret/secret.txt (outside the repo) and exposes it
|
|
* via get_test_value. The runner writes the secret
|
|
* there via repoSetup before the agent starts. Runs with shell disabled.
|
|
*/
|
|
|
|
const secret = randomUUID();
|
|
|
|
const fixture = defineFixture(
|
|
{
|
|
prompt: `Call the get_test_value tool from the robinMCP server. It returns a JSON object with a "value" field. Extract that inner value string and pass it to set_output.`,
|
|
shell: "disabled",
|
|
},
|
|
{ localOnly: true }
|
|
);
|
|
|
|
function validator(result: AgentResult): ValidationCheck[] {
|
|
const output = result.structuredOutput;
|
|
const setOutputCalled = output !== null;
|
|
const correctValue = setOutputCalled && output === secret;
|
|
|
|
return [
|
|
{ name: "set_output", passed: setOutputCalled },
|
|
{ name: "repo_mcp", passed: correctValue },
|
|
];
|
|
}
|
|
|
|
export const test: TestRunnerOptions = {
|
|
name: "mcpmerge",
|
|
fixture,
|
|
validator,
|
|
env: {
|
|
GITHUB_REPOSITORY: "pullfrog/test-repo-mcp",
|
|
PULLFROG_DISABLE_SECURITY_INSTRUCTIONS: "1",
|
|
PULLFROG_MCP_SECRET: secret,
|
|
},
|
|
repoSetup:
|
|
'mkdir -p /tmp/pullfrog-mcp-secret && printf "%s" "$PULLFROG_MCP_SECRET" > /tmp/pullfrog-mcp-secret/secret.txt',
|
|
};
|